Characterization of Architectural Distortion in Mammograms Based on Texture Analysis Using Support Vector Machine Classifier with Clinical Evaluation.

Architecture distortion (AD) is an important and early sign of breast cancer, but due to its subtlety, it is often missed on the screening mammograms. The objective of this study is to create a quantitative approach for texture classification of AD based on various texture models, using support vector machine (SVM) classifier. The texture analysis has been done on the region of interest (ROI) selected from the original mammogram. A comprehensive analysis has been done on samples from three databases; out of which, two data sets are from the public domain, and the third data set is for clinical evaluation. The public domain databases are IRMA version of digital database for screening mammogram (DDSM) and Mammographic Image Analysis Society (MIAS). For clinical evaluation, the actual patient's database has been obtained from ACE Healthways, Diagnostic Centre Ludhiana, India. The significant finding of proposed study lies in appropriate selection of the size of ROIs. The experiments have been done on fixed size of ROIs as well as on the ground truth (variable size) ROIs. Best results pertain to an accuracy of 92.94 % obtained in case of DDSM database for fixed-size ROIs. In case of MIAS database, an accuracy of 95.34 % is achieved in AD versus non-AD (normal) cases for ground truth ROIs. Clinically, an accuracy of 88 % was achieved for ACE dataset. The results obtained in the present study are encouraging, as optimal result has been achieved for the proposed study in comparison with other related work in the same area.

Reversible left ventricular dysfunction and acute kidney injury in a patient with nonamyloid light chain deposition disease.

Non-amyloid light chain deposition disease (LCDD) is a rare entity that most commonly presents as proteinuria and/or renal dysfunction. We report on a patient who initially presented with acutely decompensated heart failure and subsequently developed nephrotic range proteinuria with attendant advanced renal dysfunction. The diagnosis of LCCD was made on renal biopsy.She was treated with five cycles of bortezomib and dexamethasone followed by cyclophosphamide priming for peripheral blood stem cell (PBSC) mobilization and auto logousstem cell transplant (ASCT). Four years later, she remains in very good partial response (VGPR) with a left ventricular ejection fraction (LVEF) of 58% and serum creatinine of 1.1 mg/dl. This observation supports the approach of aggressive management of patients with LCDD who have multiple organ failure.

New heparin dosing regimen for diabetics undergoing percutaneous coronary intervention.

It has been previously demonstrated that diabetics are less sensitive to heparin compared to non-diabetics. We hypothesized that an initial heparin dose of 80 IU per kilogram administered to diabetics rather than 70 IU per kilogram might yield a more optimal initial ACT of 300 to 350 seconds when glycoprotein IIb/IIIa receptor antagonists are not used. We prospectively studied 130 elective PCI patients without diabetes treated with 70 IU per kilogram of unfractionated heparin and 81 elective PCI patients with diabetes treated with 80 IU per kilogram, and compared the initially achieved ACT. The mean heparin dose given per kg was greater (by intention) in diabetics versus non-diabetics. Despite that, there was no significant difference in the initially achieved ACT in diabetics and non-diabetics.